Computers & Electrical Engineering最新文献_第3页

Optimizing integrated energy systems at park level: A cooperative game approach with exergy economics 在公园层面优化综合能源系统：采用放能经济学的合作博弈方法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-09 DOI: 10.1016/j.compeleceng.2024.109762

This study presents a comprehensive framework for optimizing energy systems by integrating exergy analysis, energy economics, and game theory. The concept of exergy, which quantifies the usable energy within a system, is employed to evaluate energy efficiency and losses across various energy sources, including thermal, cooling, chemical, and electrical systems. Stoichiometric coefficients, denoted by the factor λ, are utilized to simplify exergy calculations for different energy types and processes. The economic evaluation of energy flows is conducted through energy economics principles, incorporating cost allocation and balance equations. The integration of game theory into the optimization model ensures strategic interactions among energy components, leading to a Nash equilibrium that balances economic performance, efficiency, and environmental sustainability. The model also accounts for emissions and the required proportion of renewable energy. To solve the complex optimization problem, a modified Particle Swarm Optimization (PSO) algorithm is employed, featuring adaptive mechanisms for velocity and inertia updates, enhancing the search process for the optimal solution. The proposed framework is designed to optimize the Integrated Energy System (IES) efficiently, ensuring sustainable and economically viable energy management. The analysis of optimization strategies highlights a trade-off between cost and efficiency. Strategy 1, focused on minimizing cost, achieves the lowest cost at 4069.37 CNY, 25.79 % less than Strategy 2, but with a reduced exergy efficiency of 59.82 %, which is 10.14 % lower than Strategy 2′s 68.47 %. Strategy 3 offers a balanced approach, with a cost of 4970.89 CNY, 9.43 % higher than Strategy 1 but 9.43 % lower than Strategy 2. It achieves an exergy efficiency of 67.87 %, only 0.60 % lower than Strategy 2, thus providing a practical compromise between economic performance and efficiency.

本研究通过整合放能分析、能源经济学和博弈论，提出了优化能源系统的综合框架。外能概念量化了系统内的可用能量，用于评估各种能源（包括热能、冷却、化学和电力系统）的能效和损耗。用系数 λ 表示的化学计量系数可简化不同能源类型和流程的放能计算。通过能源经济学原理，结合成本分配和平衡方程，对能量流进行经济评估。将博弈论融入优化模型，可确保能源成分之间的战略互动，从而实现纳什均衡，平衡经济绩效、效率和环境可持续性。该模型还考虑了排放量和所需的可再生能源比例。为解决复杂的优化问题，采用了一种改进的粒子群优化（PSO）算法，其特点是速度和惯性更新的自适应机制，增强了最佳解决方案的搜索过程。所提出的框架旨在有效优化综合能源系统（IES），确保可持续和经济可行的能源管理。对优化策略的分析凸显了成本与效率之间的权衡。策略 1 侧重于成本最小化，实现了最低成本 4069.37 元人民币，比策略 2 低 25.79%，但放能效率降低到 59.82%，比策略 2 的 68.47% 低 10.14%。策略 3 提供了一种平衡的方法，其成本为 4970.89 元人民币，比策略 1 高 9.43%，但比策略 2 低 9.43%；其放能效率为 67.87%，仅比策略 2 低 0.60%，从而在经济性能和效率之间实现了切实可行的折中。

{"title":"Optimizing integrated energy systems at park level: A cooperative game approach with exergy economics","authors":"","doi":"10.1016/j.compeleceng.2024.109762","DOIUrl":"10.1016/j.compeleceng.2024.109762","url":null,"abstract":"<div><div>This study presents a comprehensive framework for optimizing energy systems by integrating exergy analysis, energy economics, and game theory. The concept of exergy, which quantifies the usable energy within a system, is employed to evaluate energy efficiency and losses across various energy sources, including thermal, cooling, chemical, and electrical systems. Stoichiometric coefficients, denoted by the factor λ, are utilized to simplify exergy calculations for different energy types and processes. The economic evaluation of energy flows is conducted through energy economics principles, incorporating cost allocation and balance equations. The integration of game theory into the optimization model ensures strategic interactions among energy components, leading to a Nash equilibrium that balances economic performance, efficiency, and environmental sustainability. The model also accounts for emissions and the required proportion of renewable energy. To solve the complex optimization problem, a modified Particle Swarm Optimization (PSO) algorithm is employed, featuring adaptive mechanisms for velocity and inertia updates, enhancing the search process for the optimal solution. The proposed framework is designed to optimize the Integrated Energy System (IES) efficiently, ensuring sustainable and economically viable energy management. The analysis of optimization strategies highlights a trade-off between cost and efficiency. Strategy 1, focused on minimizing cost, achieves the lowest cost at 4069.37 CNY, 25.79 % less than Strategy 2, but with a reduced exergy efficiency of 59.82 %, which is 10.14 % lower than Strategy 2′s 68.47 %. Strategy 3 offers a balanced approach, with a cost of 4970.89 CNY, 9.43 % higher than Strategy 1 but 9.43 % lower than Strategy 2. It achieves an exergy efficiency of 67.87 %, only 0.60 % lower than Strategy 2, thus providing a practical compromise between economic performance and efficiency.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MPLNet: Multi-task supervised progressive learning network for diabetic retinopathy grading MPLNet：用于糖尿病视网膜病变分级的多任务监督渐进学习网络

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-08 DOI: 10.1016/j.compeleceng.2024.109746

Diabetic Retinopathy (DR) is a retinal disease resulting from diabetes. In severe cases, it can lead to irreversible damage to the retina or even blindness. Employing deep learning models to assist in DR diagnosis and classification can alleviate the burden of screening. However, challenges such as the tendency of models to overlook subtle lesions (e.g., microaneurysms) in retinal images and the imbalance in DR data distribution hinder accurate grading. To address these issues, this paper proposes a multi-task supervised progressive learning network (MPLNet) consisting of a Lesion-aware feature extraction Module (LFM) and a Category feature extraction Module (CFM). The network utilizes two progressive tasks – DR identification and DR grading – to guide the LFM and CFM in extracting comprehensive lesion information and then learning discriminative features for each category, thereby enhancing the performance of DR grading. Additionally, to improve the feature extraction capabilities of the two modules, this paper introduces the Detail Attention Module (DAM) and the Category Attention Module (CAM). DAM enhances the detection ability of tiny abnormal areas in the retinal images from both channel and spatial dimensions. The CAM thoroughly explores the critical features of each category from multiple dimensions, thereby reducing the impact of data imbalance. The proposed method achieved kappa scores of 87.0%, 88.2%, and 93.0% on the DDR, Messidor-2, and APTOS datasets, respectively. Experimental results demonstrate that MPLNet outperforms other DR grading methods. T-SNE and Grad-CAM visualization techniques verify the interpretability of the model.

糖尿病视网膜病变（DR）是一种由糖尿病引起的视网膜疾病。严重时可导致视网膜不可逆转的损伤，甚至失明。采用深度学习模型协助诊断和分类糖尿病视网膜病变可以减轻筛查负担。然而，模型容易忽略视网膜图像中的细微病变（如微动脉瘤）以及 DR 数据分布不平衡等挑战阻碍了准确分级。为了解决这些问题，本文提出了一种由病变感知特征提取模块（LFM）和类别特征提取模块（CFM）组成的多任务监督渐进学习网络（MPLNet）。该网络利用两个渐进任务--DR 识别和 DR 分级--指导 LFM 和 CFM 提取全面的病变信息，然后学习每个类别的判别特征，从而提高 DR 分级的性能。此外，为了提高两个模块的特征提取能力，本文还引入了细节关注模块（DAM）和类别关注模块（CAM）。DAM 从通道和空间两个维度增强了对视网膜图像中微小异常区域的检测能力。类别关注模块从多个维度深入挖掘每个类别的关键特征，从而减少数据不平衡的影响。所提出的方法在 DDR、Messidor-2 和 APTOS 数据集上的 kappa 分数分别达到了 87.0%、88.2% 和 93.0%。实验结果表明，MPLNet优于其他DR分级方法。T-SNE 和 Grad-CAM 可视化技术验证了模型的可解释性。

{"title":"MPLNet: Multi-task supervised progressive learning network for diabetic retinopathy grading","authors":"","doi":"10.1016/j.compeleceng.2024.109746","DOIUrl":"10.1016/j.compeleceng.2024.109746","url":null,"abstract":"<div><div>Diabetic Retinopathy (DR) is a retinal disease resulting from diabetes. In severe cases, it can lead to irreversible damage to the retina or even blindness. Employing deep learning models to assist in DR diagnosis and classification can alleviate the burden of screening. However, challenges such as the tendency of models to overlook subtle lesions (e.g., microaneurysms) in retinal images and the imbalance in DR data distribution hinder accurate grading. To address these issues, this paper proposes a multi-task supervised progressive learning network (MPLNet) consisting of a Lesion-aware feature extraction Module (LFM) and a Category feature extraction Module (CFM). The network utilizes two progressive tasks – DR identification and DR grading – to guide the LFM and CFM in extracting comprehensive lesion information and then learning discriminative features for each category, thereby enhancing the performance of DR grading. Additionally, to improve the feature extraction capabilities of the two modules, this paper introduces the Detail Attention Module (DAM) and the Category Attention Module (CAM). DAM enhances the detection ability of tiny abnormal areas in the retinal images from both channel and spatial dimensions. The CAM thoroughly explores the critical features of each category from multiple dimensions, thereby reducing the impact of data imbalance. The proposed method achieved kappa scores of 87.0%, 88.2%, and 93.0% on the DDR, Messidor-2, and APTOS datasets, respectively. Experimental results demonstrate that MPLNet outperforms other DR grading methods. T-SNE and Grad-CAM visualization techniques verify the interpretability of the model.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A bibliometric survey on impact of Blockchain in Robotics: Trends and Applications 区块链对机器人技术影响的文献计量调查：趋势与应用

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-08 DOI: 10.1016/j.compeleceng.2024.109744

Integrating blockchain technology within robotic systems holds great potential for substantial breakthroughs, not only in industrial environments but in several avenues such as agriculture, healthcare, supply chain, and so on, which require increased levels of autonomy and security. This bibliometric survey comprehensively examines the evolution and interplay between blockchain technology and robotics. Addressing the inception of this domain, the study analyses research trends, publication shifts, influential academic articles, authors, countries, and so on. The influence of emerging themes, such as Industry 4.0, Artificial intelligence, and the Internet of Things, are also explored, elucidating their impact on the research trajectory. Utilizing bibliometric techniques, the review offers insights into the current state of blockchain applications in robotic systems and suggests potential future directions warranting in-depth exploration. For a holistic overview covering both literature and technological advancements, we also present patent landscaping on blockchain in robotics, bridging the gap between theoretical results and real-world applications. To the best of our knowledge, this is the first work to present the bibliometric approach of reviewing the literature and patents for blockchain in robotics, precisely via bibliometric techniques such as keyword co-occurrence network, co-citation network, thematic evolution, and Sankey graph.

将区块链技术整合到机器人系统中，不仅在工业环境中，而且在农业、医疗保健、供应链等多个需要提高自主性和安全性的领域中，都具有实现重大突破的巨大潜力。本文献计量学调查全面研究了区块链技术与机器人技术之间的演变和相互作用。针对这一领域的开端，本研究分析了研究趋势、出版变化、有影响力的学术文章、作者、国家等。研究还探讨了工业 4.0、人工智能和物联网等新兴主题的影响，阐明了它们对研究轨迹的影响。利用文献计量学技术，综述深入分析了区块链在机器人系统中的应用现状，并提出了值得深入探讨的潜在未来方向。为了对文献和技术进步进行全面概述，我们还介绍了机器人技术中的区块链专利景观，从而弥合理论成果和实际应用之间的差距。据我们所知，这是第一部采用文献计量学方法，通过关键词共现网络、共引网络、主题演化和桑基图等文献计量学技术，对机器人技术中的区块链进行文献和专利综述的著作。

{"title":"A bibliometric survey on impact of Blockchain in Robotics: Trends and Applications","authors":"","doi":"10.1016/j.compeleceng.2024.109744","DOIUrl":"10.1016/j.compeleceng.2024.109744","url":null,"abstract":"<div><div>Integrating blockchain technology within robotic systems holds great potential for substantial breakthroughs, not only in industrial environments but in several avenues such as agriculture, healthcare, supply chain, and so on, which require increased levels of autonomy and security. This bibliometric survey comprehensively examines the evolution and interplay between blockchain technology and robotics. Addressing the inception of this domain, the study analyses research trends, publication shifts, influential academic articles, authors, countries, and so on. The influence of emerging themes, such as Industry 4.0, Artificial intelligence, and the Internet of Things, are also explored, elucidating their impact on the research trajectory. Utilizing bibliometric techniques, the review offers insights into the current state of blockchain applications in robotic systems and suggests potential future directions warranting in-depth exploration. For a holistic overview covering both literature and technological advancements, we also present patent landscaping on blockchain in robotics, bridging the gap between theoretical results and real-world applications. To the best of our knowledge, this is the first work to present the bibliometric approach of reviewing the literature and patents for blockchain in robotics, precisely via bibliometric techniques such as keyword co-occurrence network, co-citation network, thematic evolution, and Sankey graph.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Real-time monitoring and control of a PV-fed enhanced cubic voltage gain converter for DC microgrid 用于直流微电网的光伏供电增强型立方电压增益转换器的实时监测和控制

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-07 DOI: 10.1016/j.compeleceng.2024.109761

In this manuscript, a novel high-gain DC-DC converter with an ultra-step-up voltage gain value of 22.2 is introduced along with a custom-developed web application for remotely monitoring and controlling the power converter. The proposed converter is synthesized using two stages – stage 1 yields a cubic voltage gain and stage employs a diode-capacitor gain cell (DCGC) to reduce the voltage stress on the switch. The proposed gain extension hypothesis is experimentally validated through an 18 V to 400 V, 175 W prototype converter which delivers 175 W to the load at a 93.5% efficiency. The proposed converter exhibits excellent dynamic response when regulating the output voltage to 400 V over a wide range of input voltage and load current variations; the overshoots and undershoots are also negligible. Further, the maximum voltage stress on the switch is only 37.5% of the output voltage. For remotely controlling and monitoring the converter under real-time conditions with a high sampling rate, a web application is developed using React.js. The STM32 microcontroller is programmed to transmit data serially to the server, which then interacts with the web application using hypertext transfer protocol (HTTP) and WebSockets. The effectiveness of the developed interface is also practically verified by controlling the proposed converter in various modes viz., open-loop, soft-start, constant voltage, constant current, soft-stop, load regulation and overvoltage protection modes. Based on the comparison with several converters the proposed converter possesses unique advantages. Additionally, its web-based remote monitoring and control features are preferable for DC microgrid application.

本手稿介绍了一种新型高增益直流-直流转换器，其超升电压增益值为 22.2，同时还介绍了一种定制开发的网络应用程序，用于远程监控电源转换器。拟议的转换器采用两级合成--第一级产生立方电压增益，第二级采用二极管电容器增益单元 (DCGC)，以降低开关上的电压压力。所提出的增益扩展假设通过一个 18 V 至 400 V、175 W 的原型转换器进行了实验验证，该转换器能以 93.5% 的效率向负载提供 175 W 的功率。在输入电压和负载电流变化范围很宽的情况下，将输出电压调节到 400 V 时，拟议的转换器表现出卓越的动态响应；过冲和欠冲也可以忽略不计。此外，开关上的最大电压应力仅为输出电压的 37.5%。为了在高采样率的实时条件下远程控制和监控转换器，使用 React.js 开发了一个网络应用程序。对 STM32 微控制器进行编程，使其向服务器串行传输数据，然后服务器使用超文本传输协议（HTTP）和 WebSockets 与网络应用程序进行交互。通过在各种模式（即开环、软启动、恒压、恒流、软停止、负载调节和过压保护模式）下控制所提议的转换器，还实际验证了所开发接口的有效性。根据与几种变流器的比较，拟议的变流器具有独特的优势。此外，其基于网络的远程监测和控制功能更适合直流微电网应用。

{"title":"Real-time monitoring and control of a PV-fed enhanced cubic voltage gain converter for DC microgrid","authors":"","doi":"10.1016/j.compeleceng.2024.109761","DOIUrl":"10.1016/j.compeleceng.2024.109761","url":null,"abstract":"<div><div>In this manuscript, a novel high-gain DC-DC converter with an ultra-step-up voltage gain value of 22.2 is introduced along with a custom-developed web application for remotely monitoring and controlling the power converter. The proposed converter is synthesized using two stages – stage 1 yields a cubic voltage gain and stage employs a diode-capacitor gain cell (DCGC) to reduce the voltage stress on the switch. The proposed gain extension hypothesis is experimentally validated through an 18 V to 400 V, 175 W prototype converter which delivers 175 W to the load at a 93.5% efficiency. The proposed converter exhibits excellent dynamic response when regulating the output voltage to 400 V over a wide range of input voltage and load current variations; the overshoots and undershoots are also negligible. Further, the maximum voltage stress on the switch is only 37.5% of the output voltage. For remotely controlling and monitoring the converter under real-time conditions with a high sampling rate, a web application is developed using React.js. The STM32 microcontroller is programmed to transmit data serially to the server, which then interacts with the web application using hypertext transfer protocol (HTTP) and WebSockets. The effectiveness of the developed interface is also practically verified by controlling the proposed converter in various modes viz., open-loop, soft-start, constant voltage, constant current, soft-stop, load regulation and overvoltage protection modes. Based on the comparison with several converters the proposed converter possesses unique advantages. Additionally, its web-based remote monitoring and control features are preferable for DC microgrid application.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised industry anomaly detection via asymmetric reverse distillation 通过非对称反向提炼进行无监督工业异常检测

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-05 DOI: 10.1016/j.compeleceng.2024.109759

Existing unsupervised industry anomaly detection methods often rely on convolutional operations to capture fine-grained details in images. However, they may overlook crucial global context embeddings that are essential for accurate industry anomaly detection. To tackle this issue, we propose a global attention module, known as Global Attention with Spatial location and Content (GASC), which extracts global embeddings by considering both spatial information and content, thus compensating for the limitations of convolutional operations. Moreover, we introduce a novel residual unit with GASC and pre-activation in the student network, resulting in an asymmetric reverse distillation network (ARD). This architecture addresses the problem faced by previous methods where teacher and student networks share identical or similar structures, making it challenging to extract distinctive features for industry anomaly detection. Furthermore, to enable ARD to detect anomalies of various sizes, we incorporate both local details and global semantics by comparing the discrepancies between teacher and student network embeddings using cosine similarity at multiple scales. Finally, our approach is extensively evaluated through quantitative and qualitative experiments conducted on the MVTec, BTAD and KolektorSDD2 datasets, showcasing the outstanding anomaly detection performance and generalizability of our method.

现有的无监督行业异常检测方法通常依赖卷积运算来捕捉图像中的细粒度细节。然而，这些方法可能会忽略关键的全局上下文嵌入，而这对于准确的行业异常检测至关重要。为了解决这个问题，我们提出了一种全局注意力模块，即 "带空间位置和内容的全局注意力（GASC）"，它通过同时考虑空间信息和内容来提取全局嵌入，从而弥补了卷积运算的局限性。此外，我们还在学生网络中引入了具有 GASC 和预激活功能的新型残差单元，从而形成了非对称反向蒸馏网络（ARD）。这种架构解决了以往方法所面临的问题，即教师和学生网络具有相同或相似的结构，这使得为行业异常检测提取独特特征具有挑战性。此外，为了使 ARD 能够检测到各种规模的异常，我们通过在多个尺度上使用余弦相似度来比较教师和学生网络嵌入之间的差异，从而将局部细节和全局语义结合起来。最后，我们在 MVTec、BTAD 和 KolektorSDD2 数据集上进行了定量和定性实验，对我们的方法进行了广泛评估，展示了我们的方法出色的异常检测性能和普适性。

{"title":"Unsupervised industry anomaly detection via asymmetric reverse distillation","authors":"","doi":"10.1016/j.compeleceng.2024.109759","DOIUrl":"10.1016/j.compeleceng.2024.109759","url":null,"abstract":"<div><div>Existing unsupervised industry anomaly detection methods often rely on convolutional operations to capture fine-grained details in images. However, they may overlook crucial global context embeddings that are essential for accurate industry anomaly detection. To tackle this issue, we propose a global attention module, known as Global Attention with Spatial location and Content (GASC), which extracts global embeddings by considering both spatial information and content, thus compensating for the limitations of convolutional operations. Moreover, we introduce a novel residual unit with GASC and pre-activation in the student network, resulting in an asymmetric reverse distillation network (ARD). This architecture addresses the problem faced by previous methods where teacher and student networks share identical or similar structures, making it challenging to extract distinctive features for industry anomaly detection. Furthermore, to enable ARD to detect anomalies of various sizes, we incorporate both local details and global semantics by comparing the discrepancies between teacher and student network embeddings using cosine similarity at multiple scales. Finally, our approach is extensively evaluated through quantitative and qualitative experiments conducted on the MVTec, BTAD and KolektorSDD2 datasets, showcasing the outstanding anomaly detection performance and generalizability of our method.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hierarchical MPC-based authority allocation strategy for human–machine shared vehicles considering human–machine conflict 考虑人机冲突的人机共用车辆基于分层 MPC 的权限分配策略

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-05 DOI: 10.1016/j.compeleceng.2024.109736

The uncertainty of driver behavior is an important factor affecting the safety of human–machine co-driving vehicles. Traditional rule-based models often fail to capture the nonlinear and complex characteristics of human steering behavior. To overcome this, we propose a data network-driven approach utilizing gated recurrent unit (GRU) neural networks to accurately predict driver steering behavior. The GRU-based driver model is integrated with vehicle dynamics to construct a control-oriented driver–vehicle model. Considering that human–machine conflict may cause vehicle instability, an exponential function combining proportional–integral–derivative is proposed to quantify the human–machine conflict level based on steering difference. To reasonably allocate human–computer permissions based on human–machine interaction, a hierarchical authority allocation framework is proposed. The upper layer provides a reference authority allocation via an exponential function, while the lower layer employs a real-time model predictive control (MPC) optimizer to track this reference, ensuring optimal vehicle path tracking and stability. The proposed system’s effectiveness is validated through driver-in-the-loop testing, demonstrating significant improvements in safety and performance. The results show that in the human–machine conflict scenario, the proposed authority allocation strategy can still ensure the path tracking and safety of the vehicle.

驾驶员行为的不确定性是影响人机共驾车辆安全性的一个重要因素。传统的基于规则的模型往往无法捕捉到人类转向行为的非线性和复杂特性。为了克服这一问题，我们提出了一种数据网络驱动的方法，利用门控递归单元（GRU）神经网络来准确预测驾驶员的转向行为。基于 GRU 的驾驶员模型与车辆动力学相结合，构建了面向控制的驾驶员-车辆模型。考虑到人机冲突可能导致车辆的不稳定性，提出了一个结合了比例-积分-衍生的指数函数来量化基于转向差异的人机冲突程度。为了在人机交互的基础上合理分配人机权限，提出了分层权限分配框架。上层通过指数函数提供参考权限分配，而下层则采用实时模型预测控制（MPC）优化器来跟踪该参考值，从而确保最佳的车辆路径跟踪和稳定性。通过驾驶员在环测试验证了拟议系统的有效性，证明其在安全性和性能方面均有显著改善。结果表明，在人机冲突情况下，所提出的权限分配策略仍能确保车辆的路径跟踪和安全性。

{"title":"Hierarchical MPC-based authority allocation strategy for human–machine shared vehicles considering human–machine conflict","authors":"","doi":"10.1016/j.compeleceng.2024.109736","DOIUrl":"10.1016/j.compeleceng.2024.109736","url":null,"abstract":"<div><div>The uncertainty of driver behavior is an important factor affecting the safety of human–machine co-driving vehicles. Traditional rule-based models often fail to capture the nonlinear and complex characteristics of human steering behavior. To overcome this, we propose a data network-driven approach utilizing gated recurrent unit (GRU) neural networks to accurately predict driver steering behavior. The GRU-based driver model is integrated with vehicle dynamics to construct a control-oriented driver–vehicle model. Considering that human–machine conflict may cause vehicle instability, an exponential function combining proportional–integral–derivative is proposed to quantify the human–machine conflict level based on steering difference. To reasonably allocate human–computer permissions based on human–machine interaction, a hierarchical authority allocation framework is proposed. The upper layer provides a reference authority allocation via an exponential function, while the lower layer employs a real-time model predictive control (MPC) optimizer to track this reference, ensuring optimal vehicle path tracking and stability. The proposed system’s effectiveness is validated through driver-in-the-loop testing, demonstrating significant improvements in safety and performance. The results show that in the human–machine conflict scenario, the proposed authority allocation strategy can still ensure the path tracking and safety of the vehicle.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PB-Trajectron: Physics bounded neural network for generalized trajectory prediction PB-Trajectron：用于广义轨迹预测的物理有界神经网络

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-04 DOI: 10.1016/j.compeleceng.2024.109743

Vehicle trajectory prediction is a critical technology in autonomous driving systems, as the quality of prediction directly affects downstream path planning and vehicle control. Although recent studies have shown that models combining kinematic rules with data-driven methods exhibit better interpretability in trajectory prediction, these models often adopt fixed constraint strengths, limiting their generalization ability in diverse traffic scenarios. This fixed constraint strength design restricts the model’s adaptability to different traffic environments.

To address this issue, we propose PB-Trajectron, a dynamic integration mechanism that enhances the model’s prediction performance and generalization capability. PB-Trajectron is a dynamic integration mechanism that combines vehicle kinematic rules with deep learning prediction models for generalized vehicle trajectory prediction. The model integrates physics-based motion models and Deep Neural Networks (DNNs) to provide reasonable physical explanations for predicting vehicle trajectories at different speeds. First, we establish two vehicle kinematic constraints applicable to different prediction scenarios, enabling the agent to switch between these constraints based on the causal relationships between vehicle motion states to avoid generating non-physical trajectory results. Second, we propose a kinematic constraint decision framework based on velocity thresholds, which demonstrates adaptive adjustment, allowing the agent to switch tasks according to real-time state conditions and adaptively adjust the contribution of different physical constraints based on actual vehicle speeds. Finally, we investigate the advantages of PB-Trajectron in Out-of-Domain(OOD) generalization.

Cross-scenario experiments on the nuScenes dataset show that, compared to previous methods, PB-Trajectron reduces the final displacement error by 7.69% when the prediction step length is 4. Furthermore, out-of-domain generalization tests on the INTERACTION dataset demonstrate that PB-Trajectron achieves a 12.23% reduction in average prediction error on datasets from different countries and scenarios compared to previous methods. The proposed mechanism can better adapt to complex and diverse traffic scenarios, laying the foundation for explainable and robust autonomous driving systems.

车辆轨迹预测是自动驾驶系统中的一项关键技术，因为预测质量直接影响下游路径规划和车辆控制。尽管最近的研究表明，运动学规则与数据驱动方法相结合的模型在轨迹预测中表现出更好的可解释性，但这些模型通常采用固定的约束强度，限制了它们在不同交通场景中的泛化能力。为了解决这个问题，我们提出了 PB-Trajectron，一种能提高模型预测性能和泛化能力的动态集成机制。PB-Trajectron 是一种动态集成机制，它将车辆运动学规则与深度学习预测模型相结合，用于通用车辆轨迹预测。该模型集成了基于物理的运动模型和深度神经网络（DNN），为预测不同速度下的车辆轨迹提供了合理的物理解释。首先，我们建立了两种适用于不同预测场景的车辆运动学约束，使代理能够根据车辆运动状态之间的因果关系在这些约束之间进行切换，以避免生成非物理轨迹结果。其次，我们提出了一个基于速度阈值的运动约束决策框架，该框架展示了自适应调整功能，允许代理根据实时状态条件切换任务，并根据实际车速自适应调整不同物理约束的贡献。最后，我们研究了PB-Trajectron在域外（OOD）泛化方面的优势。在nuScenes数据集上进行的跨场景实验表明，与之前的方法相比，当预测步长为4时，PB-Trajectron可将最终位移误差降低7.69%。此外，在INTERACTION数据集上进行的域外泛化测试表明，与之前的方法相比，PB-Trajectron在不同国家和场景的数据集上可将平均预测误差降低12.23%。所提出的机制能更好地适应复杂多样的交通场景，为可解释且稳健的自动驾驶系统奠定了基础。

{"title":"PB-Trajectron: Physics bounded neural network for generalized trajectory prediction","authors":"","doi":"10.1016/j.compeleceng.2024.109743","DOIUrl":"10.1016/j.compeleceng.2024.109743","url":null,"abstract":"<div><div>Vehicle trajectory prediction is a critical technology in autonomous driving systems, as the quality of prediction directly affects downstream path planning and vehicle control. Although recent studies have shown that models combining kinematic rules with data-driven methods exhibit better interpretability in trajectory prediction, these models often adopt fixed constraint strengths, limiting their generalization ability in diverse traffic scenarios. This fixed constraint strength design restricts the model’s adaptability to different traffic environments.</div><div>To address this issue, we propose PB-Trajectron, a dynamic integration mechanism that enhances the model’s prediction performance and generalization capability. PB-Trajectron is a dynamic integration mechanism that combines vehicle kinematic rules with deep learning prediction models for generalized vehicle trajectory prediction. The model integrates physics-based motion models and <u>D</u>eep <u>N</u>eural <u>N</u>etworks (DNNs) to provide reasonable physical explanations for predicting vehicle trajectories at different speeds. First, we establish two vehicle kinematic constraints applicable to different prediction scenarios, enabling the agent to switch between these constraints based on the causal relationships between vehicle motion states to avoid generating non-physical trajectory results. Second, we propose a kinematic constraint decision framework based on velocity thresholds, which demonstrates adaptive adjustment, allowing the agent to switch tasks according to real-time state conditions and adaptively adjust the contribution of different physical constraints based on actual vehicle speeds. Finally, we investigate the advantages of PB-Trajectron in <u>O</u>ut-<u>o</u>f-<u>D</u>omain(OOD) generalization.</div><div>Cross-scenario experiments on the nuScenes dataset show that, compared to previous methods, PB-Trajectron reduces the final displacement error by 7.69% when the prediction step length is 4. Furthermore, out-of-domain generalization tests on the INTERACTION dataset demonstrate that PB-Trajectron achieves a 12.23% reduction in average prediction error on datasets from different countries and scenarios compared to previous methods. The proposed mechanism can better adapt to complex and diverse traffic scenarios, laying the foundation for explainable and robust autonomous driving systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ZMAR-SNFlow:Restoration for low-light images with massive zero-element pixels ZMAR-SNFlow：使用大量零元素像素修复低照度图像

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-04 DOI: 10.1016/j.compeleceng.2024.109750

Under real-world extremely low-light conditions, many low-light RGB (Red, Green, Blue) images contains massive zero-element pixels (a zero-element pixel is defined as that a color pixel with three RGB values contain no less than one zero). Low-light images with massive zero-element pixels suffer both light weakness and information loss. Existing low-light image enhancement methods aim to amplify the low-light, whereas seldomly consider to restore the information loss caused by massive zero-element pixels. To tackle above issue, firstly, we construct a zero-element mask set that contains many zero-element masks from real-world extremely low-light night traffic monitoring (NTM) images. Each zero-element mask is a binary image, where 1 and 0 are corresponding to zero-element pixels and other pixels. Secondly, we propose a novel flow-based generative method ZMAR-SNFlow to restore low-light images with massive zero-element pixels. ZMAR-SNFlow consists of a zero-element mask attention based Restormer (ZMAR) encoder and a strengthened normalizing flow (SNFlow). Specifically, we proposed a zero-element mask attention (ZMA) module, which is combined with the Restormer module to form the ZMAR module, and ZMAR is used to develop the ZMAR encoder. Then, we propose to insert the unconditional affine coupling layer into the flow step of existing normalizing flow to form SNFlow. ZMAR-SNFlow learns to map the output of SNFlow into a standard normal distribution, and the inverse network of SNFlow takes the latent features of the low-light image as its input to infer the enhanced image. Finally, experimental results on benchmark datasets show that the proposed ZMAR-SNFlow can achieve state-of-the-art (SOTA) performance for low-light images with massive zero-element pixels. The source code and pre-trained models are available at https://github.com/NJUPT-IPR-ZhangBo/ZMAR-SNFlow.

在现实世界的极低照度条件下，许多低照度 RGB（红、绿、蓝）图像都包含大量零元素像素（零元素像素的定义是，一个彩色像素的三个 RGB 值中包含不少于一个零）。具有大量零元素像素的低照度图像会受到光弱和信息丢失的双重影响。现有的弱光图像增强方法主要是放大弱光，而很少考虑恢复大量零元素像素造成的信息损失。为解决上述问题，我们首先构建了一个零元素掩码集，该掩码集包含来自真实世界极低照度夜间交通监控（NTM）图像的多个零元素掩码。每个零元素掩码都是二值图像，其中 1 和 0 分别对应零元素像素和其他像素。其次，我们提出了一种新颖的基于流的生成方法 ZMAR-SNFlow，用于还原具有大量零元素像素的低照度图像。ZMAR-SNFlow 由基于零元素掩码注意的重构器（ZMAR）编码器和增强归一化流（SNFlow）组成。具体来说，我们提出了零元素掩码注意（ZMA）模块，并将其与 Restormer 模块相结合形成 ZMAR 模块，ZMAR 用于开发 ZMAR 编码器。然后，我们建议将无条件仿射耦合层插入现有归一化流程的流程步骤中，形成 SNFlow。ZMAR-SNFlow 通过学习将 SNFlow 的输出映射为标准正态分布，而 SNFlow 的逆网络将低照度图像的潜在特征作为其输入，从而推断出增强后的图像。最后，在基准数据集上的实验结果表明，所提出的 ZMAR-SNFlow 可以在具有大量零元素像素的弱光图像上实现最先进的性能（SOTA）。源代码和预训练模型可在 https://github.com/NJUPT-IPR-ZhangBo/ZMAR-SNFlow 上获取。

{"title":"ZMAR-SNFlow:Restoration for low-light images with massive zero-element pixels","authors":"","doi":"10.1016/j.compeleceng.2024.109750","DOIUrl":"10.1016/j.compeleceng.2024.109750","url":null,"abstract":"<div><div>Under real-world extremely low-light conditions, many low-light RGB (Red, Green, Blue) images contains massive zero-element pixels (a zero-element pixel is defined as that a color pixel with three RGB values contain no less than one zero). Low-light images with massive zero-element pixels suffer both light weakness and information loss. Existing low-light image enhancement methods aim to amplify the low-light, whereas seldomly consider to restore the information loss caused by massive zero-element pixels. To tackle above issue, firstly, we construct a zero-element mask set that contains many zero-element masks from real-world extremely low-light night traffic monitoring (NTM) images. Each zero-element mask is a binary image, where 1 and 0 are corresponding to zero-element pixels and other pixels. Secondly, we propose a novel flow-based generative method ZMAR-SNFlow to restore low-light images with massive zero-element pixels. ZMAR-SNFlow consists of a zero-element mask attention based Restormer (ZMAR) encoder and a strengthened normalizing flow (SNFlow). Specifically, we proposed a zero-element mask attention (ZMA) module, which is combined with the Restormer module to form the ZMAR module, and ZMAR is used to develop the ZMAR encoder. Then, we propose to insert the unconditional affine coupling layer into the flow step of existing normalizing flow to form SNFlow. ZMAR-SNFlow learns to map the output of SNFlow into a standard normal distribution, and the inverse network of SNFlow takes the latent features of the low-light image as its input to infer the enhanced image. Finally, experimental results on benchmark datasets show that the proposed ZMAR-SNFlow can achieve state-of-the-art (SOTA) performance for low-light images with massive zero-element pixels. The source code and pre-trained models are available at <span><span>https://github.com/NJUPT-IPR-ZhangBo/ZMAR-SNFlow</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust adaptive event-triggered control for unmanned surface vessel–unmanned aerial vehicle: Application to sea–air synchronized lawn mowing search operation 无人水面舰艇-无人飞行器的鲁棒自适应事件触发控制：应用于海空同步割草搜索作业

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-04 DOI: 10.1016/j.compeleceng.2024.109754

This paper investigates a robust adaptive event-triggered control algorithm with a consideration of the synchronized lawn mowing search guidance for a heterogeneous system comprising both an unmanned surface vessel (USV) and an unmanned aerial vehicle (UAV). For ensuring a cooperative global search navigation of the USV–UAV, a synchronized lawn mowing search guidance is developed with two key elements: the

L_{1}

-based virtual ship (

L_{1}

VS) and

L_{1}

-based virtual aerial (

L_{1}

VA), where the former can generate the smooth reference path for a USV according to the search task scope, while the latter can program the reference path for a UAV on the basis of its search requirements (search speed, detected capacity and communication distance). In the control loop, a robust adaptive path following control law is designed by utilizing an event-triggered mechanism and a minimal learning parameter (MLP) technique. In particular, the event-triggered mechanism has a potential role for a reduction of the unnecessary transmission resource usage for the channel of the controller to the actuator. Besides, only one learning parameters on each channel by introducing the MLP technique, implying a lower computational burden. Through the Lyapunov theorem, the semi-global uniform ultimate bounded (SGUUB) stability properties of the proposed control system. Finally, two numerical simulations are carried out to evaluate the effectiveness of the proposed strategy and the advantages compared with existing techniques.

本文研究了一种鲁棒性自适应事件触发控制算法，该算法考虑了由无人水面舰艇（USV）和无人飞行器（UAV）组成的异构系统的同步割草搜索制导。为确保 USV-UAV 的协同全局搜索导航，开发了一种同步割草搜索制导，其中包含两个关键要素：基于 L1 的虚拟船舶（L1VS）和基于 L1 的虚拟航空（L1VA），前者可根据搜索任务范围为 USV 生成平滑的参考路径，后者可根据 UAV 的搜索要求（搜索速度、探测能力和通信距离）为其编程参考路径。在控制环中，利用事件触发机制和最小学习参数（MLP）技术设计了稳健的自适应路径跟踪控制法则。其中，事件触发机制可减少控制器到执行器信道中不必要的传输资源使用。此外，通过引入 MLP 技术，每个通道只需一个学习参数，这意味着计算负担更低。通过 Lyapunov 定理，研究了所提控制系统的半全局均匀终极有界（SGUUB）稳定性。最后，通过两次数值模拟，评估了所提策略的有效性以及与现有技术相比的优势。

{"title":"Robust adaptive event-triggered control for unmanned surface vessel–unmanned aerial vehicle: Application to sea–air synchronized lawn mowing search operation","authors":"","doi":"10.1016/j.compeleceng.2024.109754","DOIUrl":"10.1016/j.compeleceng.2024.109754","url":null,"abstract":"<div><div>This paper investigates a robust adaptive event-triggered control algorithm with a consideration of the synchronized lawn mowing search guidance for a heterogeneous system comprising both an unmanned surface vessel (USV) and an unmanned aerial vehicle (UAV). For ensuring a cooperative global search navigation of the USV–UAV, a synchronized lawn mowing search guidance is developed with two key elements: the <span><math><msub><mrow><mi>L</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>-based virtual ship (<span><math><msub><mrow><mi>L</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>VS) and <span><math><msub><mrow><mi>L</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>-based virtual aerial (<span><math><msub><mrow><mi>L</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span>VA), where the former can generate the smooth reference path for a USV according to the search task scope, while the latter can program the reference path for a UAV on the basis of its search requirements (search speed, detected capacity and communication distance). In the control loop, a robust adaptive path following control law is designed by utilizing an event-triggered mechanism and a minimal learning parameter (MLP) technique. In particular, the event-triggered mechanism has a potential role for a reduction of the unnecessary transmission resource usage for the channel of the controller to the actuator. Besides, only one learning parameters on each channel by introducing the MLP technique, implying a lower computational burden. Through the Lyapunov theorem, the semi-global uniform ultimate bounded (SGUUB) stability properties of the proposed control system. Finally, two numerical simulations are carried out to evaluate the effectiveness of the proposed strategy and the advantages compared with existing techniques.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Single and multi-threaded power flow algorithm for integrated transmission-distribution-residential networks 输电-配电-住宅一体化网络的单线程和多线程电力流算法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-10-03 DOI: 10.1016/j.compeleceng.2024.109735

The rapid development of renewable sources has significantly increased interdependencies between electricity networks of all voltage levels, leading to bidirectional flows between transmission and distribution networks, and requiring analysis of Integrated Transmission-Distribution (ITD) network. The interconnectivity is further amplified by additional coupling with electricity, gas, heat and hydrogen networks, on both national and regional levels. Moreover, installation of solar, wind and storage on customers’ premises has indicated that residential networks need to be included in the overall integrated model, called Integrated Transmission-Distribution-Residential (ITDR) network. The main goal of the paper is to develop a general model of the ITD/ITDR networks and to solve the power-flow problem on large-scale networks in an efficient way. The general model includes three-phase transmission and multi-phase distribution models, as well as accurate control strategies for traditional and electronically coupled electricity resources. The proposed model is solved via novel single-threaded power flow procedure, which incorporates new network elements’ models and the developed algorithm for integrated power flow calculations in different domains. This is further improved by developing a multi-threaded approach. Analyses on a small-scale ITD network have shown that single- and multi-threaded approaches are, respectively, (1.5–4) and (2–5) times faster compared to the state-of-the-art procedures. As network size increases, the efficiency of the proposed multi-threaded procedure becomes more pronounced compared to the single-threaded one (up to 2.39 times).

可再生能源的快速发展大大增加了所有电压等级电网之间的相互依赖性，导致输电和配电网络之间的双向流动，并要求对综合输电-配电（ITD）网络进行分析。在国家和地区层面上，与电力、天然气、热力和氢气网络的额外耦合进一步增强了互联性。此外，在用户场所安装太阳能、风能和储能设备表明，住宅网络也需要纳入整体综合模型，即 "输配电一体化-住宅（ITDR）网络"。本文的主要目标是开发 ITD/ITDR 网络的通用模型，并以高效的方式解决大规模网络的电力流动问题。通用模型包括三相输电和多相配电模型，以及传统和电子耦合电力资源的精确控制策略。所提出的模型通过新颖的单线程功率流程序进行求解，该程序结合了新的网元模型和所开发的算法，用于不同领域的综合功率流计算。通过开发多线程方法，该模型得到进一步改进。对一个小规模 ITD 网络的分析表明，与最先进的程序相比，单线程方法和多线程方法分别快（1.5-4）倍和（2-5）倍。随着网络规模的扩大，建议的多线程程序的效率比单线程程序更明显（高达 2.39 倍）。

{"title":"Single and multi-threaded power flow algorithm for integrated transmission-distribution-residential networks","authors":"","doi":"10.1016/j.compeleceng.2024.109735","DOIUrl":"10.1016/j.compeleceng.2024.109735","url":null,"abstract":"<div><div>The rapid development of renewable sources has significantly increased interdependencies between electricity networks of all voltage levels, leading to bidirectional flows between transmission and distribution networks, and requiring analysis of Integrated Transmission-Distribution (ITD) network. The interconnectivity is further amplified by additional coupling with electricity, gas, heat and hydrogen networks, on both national and regional levels. Moreover, installation of solar, wind and storage on customers’ premises has indicated that residential networks need to be included in the overall integrated model, called Integrated Transmission-Distribution-Residential (ITDR) network. The main goal of the paper is to develop a general model of the ITD/ITDR networks and to solve the power-flow problem on large-scale networks in an efficient way. The general model includes three-phase transmission and multi-phase distribution models, as well as accurate control strategies for traditional and electronically coupled electricity resources. The proposed model is solved via novel <em>single-threaded</em> power flow procedure, which incorporates new network elements’ models and the developed algorithm for integrated power flow calculations in different domains. This is further improved by developing a <em>multi-threaded</em> approach. Analyses on a small-scale ITD network have shown that single- and multi-threaded approaches are, respectively, (1.5–4) and (2–5) times faster compared to the state-of-the-art procedures. As network size increases, the efficiency of the proposed multi-threaded procedure becomes more pronounced compared to the single-threaded one (up to 2.39 times).</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":4.0,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142419092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0